弱监督教师-学生框架与逐步伪掩码细化用于腺体分割
Weakly Supervised Teacher-Student Framework with Progressive Pseudo-mask Refinement for Gland Segmentation
AI总结：
本文提出一种弱监督教师-学生框架，通过稀疏病理科标注和指数移动平均稳定教师网络生成精细伪掩码，提升腺体分割的准确性和泛化能力。
摘要：
背景和目标：结直肠癌组织学分级依赖于腺体结构的准确分割。当前深度学习方法依赖于大规模像素级标注，这在常规临床实践中劳动密集且难以获得。弱监督语义分割提供了一种有前景的替代方案。然而，基于类激活图的方法往往产生不完整的伪掩码，强调高度可区分的区域，无法监督未标注的腺体结构。我们提出了一种弱监督教师-学生框架，利用稀疏病理科标注和指数移动平均稳定教师网络生成精细伪掩码。方法：该框架整合了基于置信度的过滤、教师预测与有限真实标注的自适应融合以及课程引导的细化，逐步分割未标注的腺体区域。该方法在俄亥俄州立大学韦克斯纳医学中心的机构性结直肠癌队列（包含60张经苏木精-伊红染色的全切片图像）以及公共数据集（包括腺体分割数据集、TCGA COAD、TCGA READ和SPIDER）上进行了评估。结果：在腺体分割数据集上，该框架实现了平均交并比80.10和平均Dice系数89.10。跨队列评估显示其在TCGA COAD和TCGA READ上具有良好的泛化能力，无需额外标注；而在SPIDER上表现下降，反映了领域偏移。结论：所提框架为结直肠组织学中的腺体分割提供了一种标注高效且可推广的方法。
英文摘要：
Background and objectives: Colorectal cancer histopathological grading depends on accurate segmentation of glandular structures. Current deep learning approaches rely on large scale pixel level annotations that are labor intensive and difficult to obtain in routine clinical practice. Weakly supervised semantic segmentation offers a promising alternative. However, class activation map based methods often produce incomplete pseudo masks that emphasize highly discriminative regions and fail to supervise unannotated glandular structures. We propose a weakly supervised teacher student framework that leverages sparse pathologist annotations and an Exponential Moving Average stabilized teacher network to generate refined pseudo masks. Methods: The framework integrates confidence based filtering, adaptive fusion of teacher predictions with limited ground truth, and curriculum guided refinement to progressively segment unannotated glandular regions. The method was evaluated on an institutional colorectal cancer cohort from The Ohio State University Wexner Medical Center consisting of 60 hematoxylin and eosin stained whole slide images and on public datasets including the Gland Segmentation dataset, TCGA COAD, TCGA READ, and SPIDER. Results: On the Gland Segmentation dataset the framework achieved a mean Intersection over Union of 80.10 and a mean Dice coefficient of 89.10. Cross cohort evaluation demonstrated robust generalization on TCGA COAD and TCGA READ without additional annotations, while reduced performance on SPIDER reflected domain shift. Conclusions: The proposed framework provides an annotation efficient and generalizable approach for gland segmentation in colorectal histopathology.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
